/home/tony/Work/glockenspiel/s3prl/s3prl/upstream/byol_s/byol_a/common.py:20: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call. torchaudio.set_audio_backend("sox_io") 2023-10-05 00:23:11 | WARNING | root | Pytorch pre-release version 2.1.0.dev20230831+cu118 - assuming intent to test it /home/tony/Work/glockenspiel/s3prl/s3prl/run_downstream.py:157: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call. torchaudio.set_audio_backend('sox_io') 2023-10-05 00:23:15 | INFO | fairseq.models.hubert.hubert | HubertModel Config: HubertConfig(_name='hubert', label_rate=50.0, extractor_mode='default', encoder_layers=12, encoder_embed_dim=768, encoder_ffn_embed_dim=3072, encoder_attention_heads=12, activation_fn='gelu', layer_type='transformer', dropout=0.1, attention_dropout=0.1, activation_dropout=0.0, encoder_layerdrop=0.05, dropout_input=0.1, dropout_features=0.1, final_dim=256, untie_final_proj=True, layer_norm_first=False, conv_feature_layers='[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 3', conv_bias=False, logit_temp=0.1, target_glu=False, feature_grad_mult=0.1, mask_length=10, mask_prob=0.8, mask_selection='static', mask_other=0.0, no_mask_overlap=False, mask_min_space=1, mask_channel_length=10, mask_channel_prob=0.0, mask_channel_selection='static', mask_channel_other=0.0, no_mask_channel_overlap=False, mask_channel_min_space=1, conv_pos=128, conv_pos_groups=16, conv_pos_batch_norm=False, latent_temp=[2.0, 0.5, 0.999995], skip_masked=False, skip_nomask=False, checkpoint_activations=False, required_seq_len_multiple=2, depthwise_conv_kernel_size=31, attn_type='', pos_enc_type='abs', fp16=False) /home/tony/anaconda3/envs/suno_env/lib/python3.10/site-packages/torch/nn/utils/weight_norm.py:30: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") 2023-10-05 00:23:16 | INFO | fairseq.models.hubert.hubert | cannot find dictionary. assume will be used for fine-tuning [Featurizer] - Take a list of 2 features and weighted sum them. [Featurizer] - The selected feature hidden_states's downsample rate is 960 [Runner] - Start a new experiment mert_test_8x_400k_hubert {'model_config': None, 'refresh': False} Loading model from Local mert_test_8x_400k_hubert load local model succeed load local feat extractor Wav2Vec2FeatureExtractor { "do_normalize": false, "feature_extractor_type": "Wav2Vec2FeatureExtractor", "feature_size": 1, "padding_side": "right", "padding_value": 0, "return_attention_mask": true, "sampling_rate": 24000 } load hubert model succeed overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 5%|▌ | 182/3515 [00:00<00:01, 1814.82it/s] word -> phonemes: 10%|█ | 364/3515 [00:00<00:01, 1782.52it/s] word -> phonemes: 16%|█▋ | 575/3515 [00:00<00:01, 1926.41it/s] word -> phonemes: 22%|██▏ | 776/3515 [00:00<00:01, 1955.93it/s] word -> phonemes: 28%|██▊ | 980/3515 [00:00<00:01, 1985.66it/s] word -> phonemes: 34%|███▍ | 1200/3515 [00:00<00:01, 2056.28it/s] word -> phonemes: 40%|████ | 1406/3515 [00:00<00:01, 2047.27it/s] word -> phonemes: 46%|████▌ | 1623/3515 [00:00<00:00, 2079.98it/s] word -> phonemes: 52%|█████▏ | 1832/3515 [00:00<00:00, 2041.61it/s] word -> phonemes: 58%|█████▊ | 2037/3515 [00:01<00:00, 2030.20it/s] word -> phonemes: 64%|██████▍ | 2255/3515 [00:01<00:00, 2074.40it/s] word -> phonemes: 70%|███████ | 2463/3515 [00:01<00:00, 2006.18it/s] word -> phonemes: 76%|███████▌ | 2667/3515 [00:01<00:00, 2013.98it/s] word -> phonemes: 82%|████████▏ | 2870/3515 [00:01<00:00, 2017.61it/s] word -> phonemes: 87%|████████▋ | 3073/3515 [00:01<00:00, 1982.90it/s] word -> phonemes: 93%|█████████▎| 3276/3515 [00:01<00:00, 1994.80it/s] word -> phonemes: 99%|█████████▉| 3476/3515 [00:01<00:00, 1945.33it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 1995.94it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 228/2703 [00:00<00:01, 2225.21it/s] word -> phonemes: 17%|█▋ | 451/2703 [00:00<00:01, 2159.82it/s] word -> phonemes: 25%|██▍ | 668/2703 [00:00<00:00, 2139.09it/s] word -> phonemes: 33%|███▎ | 882/2703 [00:00<00:00, 1917.84it/s] word -> phonemes: 40%|███▉ | 1077/2703 [00:00<00:00, 1918.12it/s] word -> phonemes: 48%|████▊ | 1307/2703 [00:00<00:00, 2018.17it/s] word -> phonemes: 56%|█████▋ | 1525/2703 [00:00<00:00, 2067.18it/s] word -> phonemes: 64%|██████▍ | 1733/2703 [00:00<00:00, 2031.74it/s] word -> phonemes: 73%|███████▎ | 1973/2703 [00:00<00:00, 2141.67it/s] word -> phonemes: 82%|████████▏ | 2209/2703 [00:01<00:00, 2206.89it/s] word -> phonemes: 90%|█████████ | 2446/2703 [00:01<00:00, 2255.45it/s] word -> phonemes: 99%|█████████▉| 2673/2703 [00:01<00:00, 2179.06it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2115.05it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|█ | 279/2703 [00:00<00:00, 2783.28it/s] word -> phonemes: 21%|██ | 558/2703 [00:00<00:00, 2777.99it/s] word -> phonemes: 31%|███▏ | 846/2703 [00:00<00:00, 2820.46it/s] word -> phonemes: 42%|████▏ | 1129/2703 [00:00<00:00, 2708.88it/s] word -> phonemes: 52%|█████▏ | 1403/2703 [00:00<00:00, 2719.20it/s] word -> phonemes: 63%|██████▎ | 1692/2703 [00:00<00:00, 2773.05it/s] word -> phonemes: 73%|███████▎ | 1974/2703 [00:00<00:00, 2784.57it/s] word -> phonemes: 83%|████████▎ | 2255/2703 [00:00<00:00, 2792.51it/s] word -> phonemes: 94%|█████████▍| 2535/2703 [00:00<00:00, 2774.60it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2763.16it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 203/2703 [00:00<00:01, 2025.09it/s] word -> phonemes: 15%|█▌ | 406/2703 [00:00<00:01, 2020.73it/s] word -> phonemes: 23%|██▎ | 609/2703 [00:00<00:01, 2004.78it/s] word -> phonemes: 30%|██▉ | 810/2703 [00:00<00:00, 1997.22it/s] word -> phonemes: 38%|███▊ | 1020/2703 [00:00<00:00, 2031.22it/s] word -> phonemes: 45%|████▌ | 1225/2703 [00:00<00:00, 2035.33it/s] word -> phonemes: 53%|█████▎ | 1441/2703 [00:00<00:00, 2072.76it/s] word -> phonemes: 61%|██████ | 1649/2703 [00:00<00:00, 2032.66it/s] word -> phonemes: 69%|██████▉ | 1860/2703 [00:00<00:00, 2053.59it/s] word -> phonemes: 76%|███████▋ | 2066/2703 [00:01<00:00, 2026.60it/s] word -> phonemes: 84%|████████▍ | 2276/2703 [00:01<00:00, 2047.68it/s] word -> phonemes: 92%|█████████▏| 2481/2703 [00:01<00:00, 2022.37it/s] word -> phonemes: 99%|█████████▉| 2684/2703 [00:01<00:00, 1960.32it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2011.89it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 6%|▌ | 205/3515 [00:00<00:01, 2044.37it/s] word -> phonemes: 12%|█▏ | 425/3515 [00:00<00:01, 2131.58it/s] word -> phonemes: 19%|█▊ | 658/3515 [00:00<00:01, 2219.41it/s] word -> phonemes: 26%|██▌ | 906/3515 [00:00<00:01, 2321.89it/s] word -> phonemes: 32%|███▏ | 1139/3515 [00:00<00:01, 2264.63it/s] word -> phonemes: 40%|███▉ | 1390/3515 [00:00<00:00, 2344.51it/s] word -> phonemes: 46%|████▌ | 1625/3515 [00:00<00:00, 2280.13it/s] word -> phonemes: 53%|█████▎ | 1854/3515 [00:00<00:00, 2237.60it/s] word -> phonemes: 59%|█████▉ | 2090/3515 [00:00<00:00, 2272.30it/s] word -> phonemes: 66%|██████▌ | 2318/3515 [00:01<00:00, 2226.66it/s] word -> phonemes: 72%|███████▏ | 2542/3515 [00:01<00:00, 2149.84it/s] word -> phonemes: 79%|███████▉ | 2774/3515 [00:01<00:00, 2197.53it/s] word -> phonemes: 85%|████████▌ | 2995/3515 [00:01<00:00, 2179.63it/s] word -> phonemes: 92%|█████████▏| 3230/3515 [00:01<00:00, 2226.35it/s] word -> phonemes: 98%|█████████▊| 3454/3515 [00:01<00:00, 2206.71it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2229.13it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|█ | 271/2703 [00:00<00:00, 2706.58it/s] word -> phonemes: 20%|██ | 542/2703 [00:00<00:00, 2510.44it/s] word -> phonemes: 29%|██▉ | 794/2703 [00:00<00:00, 2462.88it/s] word -> phonemes: 39%|███▉ | 1066/2703 [00:00<00:00, 2560.37it/s] word -> phonemes: 49%|████▉ | 1329/2703 [00:00<00:00, 2582.64it/s] word -> phonemes: 59%|█████▉ | 1593/2703 [00:00<00:00, 2600.16it/s] word -> phonemes: 69%|██████▊ | 1857/2703 [00:00<00:00, 2610.64it/s] word -> phonemes: 78%|███████▊ | 2119/2703 [00:00<00:00, 2516.34it/s] word -> phonemes: 88%|████████▊ | 2372/2703 [00:00<00:00, 2509.10it/s] word -> phonemes: 98%|█████████▊| 2646/2703 [00:01<00:00, 2577.58it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2562.56it/s] dev: 0%| | 0/2703 [00:00